Leaderboard / NVIDIA
Nemotron Labs Dory 1.0 4B
NVIDIA · Nemotron Labs · released 2026-10-16 · data checked 2026-11-01
Nemotron Labs Dory 1.0 4B is a 4B-parameter dense model from NVIDIA (United States), released 2026-10-16 under the OpenMDW-1.1 license. It scores 60.0 on the Small LM Index, #4 of 21 tiny models. It needs about 3.4 GB of memory at 4-bit with an 8K-token context.
Small LM Index
60.0
#4 of 21 scored tiny models
Likely 58.1–61.8 · from 3 of 6 core benchmarks
Parameters
4B
Dense
Price per 1M tokens
—
No hosted API on OpenRouter; self-host
Context window
262K
tokens
Benchmarks
Each bar shows this model's score. The tick marks the best tiny model on that benchmark. Sources: 6 reported by NVIDIA. How we label sources.
Not reported: estimated
What the index model expects from this model's other scores. Not a measurement.
MMLU-Pro≈ 79
AIME≈ 84
LiveCodeBench≈ 69
Specifications
- Lab
- NVIDIA (US · United States)
- Architecture
- Dense transformer
- Total parameters
- 4B
- Active parameters
- All (dense)
- Size class
- Tiny
- Context window
- 262K tokens
- Input modalities
- text
- Reasoning
- Reasoning (thinking)
- License
- OpenMDW-1.1
- Openness
- Open weights
- Memory to run
- ~3.4 GB at 4-bit, 8K context (more sizes)
- Hugging Face
- 10.5K downloads (30 days) · 215 likes
Compare with
- Nemotron Labs Dory 1.0 4B vs Qwen3.5 4B (4B, index 57.8)
- Nemotron Labs Dory 1.0 4B vs Qwen3 4B Thinking 2507 (4B, index 55.7)
- Nemotron Labs Dory 1.0 4B vs Spark-X2.6 4B (4.1B, index 67.5)
- Nemotron Labs Dory 1.0 4B vs Spark-X2.5 4B (4.1B, index 65.5)
Ranked in
- #7 in Best LLMs that run on an 8 GB GPU or laptop
- #9 in Best LLMs that run on a 16 GB GPU
- #5 in Best tiny LLMs for phones and edge devices
Sources
Something wrong here? Report it.
Run it locally
No GGUF build from a well-known publisher yet.
vLLM (GPU server)
vllm serve nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16Full-precision weights, for a server GPU.
Memory needed: weights, context cache and runtime buffers.
| Quantization | 4K context | 32K context | 256K context |
|---|---|---|---|
| 16-bit F16 | 8.8 GB | 9.9 GB | 18 GB |
| 8-bit Q8_0 | 5.1 GB | 6.1 GB | 15 GB |
| 4-bit Q4_K_M | 3.3 GB | 4.3 GB | 13 GB |